File size: 23,472 Bytes
7ad0442 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 |
{
"metadata": {
"total_size": 17044475904
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.0.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.1.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.10.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.11.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.12.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.13.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.13.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.14.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.14.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.14.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.14.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.14.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.14.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.14.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.14.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.14.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.15.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.15.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.15.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.15.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.15.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.15.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.15.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.15.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.15.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.16.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.16.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.16.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.16.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.16.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.17.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.18.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.19.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.2.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.20.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.20.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.21.mlp.bias": "model-00004-of-00004.safetensors",
"model.layers.21.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.21.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.21.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.21.self_attention.experts.bias": "model-00004-of-00004.safetensors",
"model.layers.21.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.21.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.21.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.21.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.22.mlp.bias": "model-00004-of-00004.safetensors",
"model.layers.22.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.22.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.22.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.22.self_attention.experts.bias": "model-00004-of-00004.safetensors",
"model.layers.22.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.22.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.22.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.22.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.23.mlp.bias": "model-00004-of-00004.safetensors",
"model.layers.23.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.23.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.23.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.23.self_attention.experts.bias": "model-00004-of-00004.safetensors",
"model.layers.23.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.23.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.23.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.23.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.3.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.4.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.5.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.6.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.6.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.7.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.8.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.9.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors"
}
}
|